Skip to content

Table from struct #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jan 25, 2018
Merged

Table from struct #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a00415e
Fix perf
Jan 24, 2018
c8cd286
Add Table.fromStruct
Jan 24, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 9 additions & 9 deletions js/perf/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,10 +144,10 @@ function createDataFrameDirectCountTest(table, column, test, value) {
let numBatches = batches.length;
for (let batchIndex = -1; ++batchIndex < numBatches;) {
// load batches
const { numRows, columns } = batches[batchIndex];
const vector = columns[colidx];
const batch = batches[batchIndex];
const vector = batch.getChildAt(colidx);
// yield all indices
for (let index = -1; ++index < numRows;) {
for (let index = -1; ++index < batch.length;) {
sum += (vector.get(index) >= value);
}
}
Expand All @@ -159,10 +159,10 @@ function createDataFrameDirectCountTest(table, column, test, value) {
let numBatches = batches.length;
for (let batchIndex = -1; ++batchIndex < numBatches;) {
// load batches
const { numRows, columns } = batches[batchIndex];
const vector = columns[colidx];
const batch = batches[batchIndex];
const vector = batch.getChildAt(colidx);
// yield all indices
for (let index = -1; ++index < numRows;) {
for (let index = -1; ++index < batch.length;) {
sum += (vector.get(index) === value);
}
}
Expand All @@ -173,7 +173,7 @@ function createDataFrameDirectCountTest(table, column, test, value) {

return {
async: true,
name: `name: '${column}', length: ${table.numRows}, type: ${table.columns[colidx].type}, test: ${test}, value: ${value}\n`,
name: `name: '${column}', length: ${table.numRows}, type: ${table.getColumnAt(colidx).type}, test: ${test}, value: ${value}\n`,
fn: op
};
}
Expand All @@ -183,7 +183,7 @@ function createDataFrameCountByTest(table, column) {

return {
async: true,
name: `name: '${column}', length: ${table.numRows}, type: ${table.columns[colidx].type}\n`,
name: `name: '${column}', length: ${table.numRows}, type: ${table.getColumnAt(colidx).type}\n`,
fn() {
table.countBy(column);
}
Expand All @@ -204,7 +204,7 @@ function createDataFrameFilterCountTest(table, column, test, value) {

return {
async: true,
name: `name: '${column}', length: ${table.numRows}, type: ${table.columns[colidx].type}, test: ${test}, value: ${value}\n`,
name: `name: '${column}', length: ${table.numRows}, type: ${table.getColumnAt(colidx).type}, test: ${test}, value: ${value}\n`,
fn() {
df.count();
}
Expand Down
10 changes: 9 additions & 1 deletion js/src/table.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,8 @@ import { Col, Predicate } from './predicate';
import { Schema, Field, Struct } from './type';
import { read, readAsync } from './ipc/reader/arrow';
import { isPromise, isAsyncIterable } from './util/compat';
import { Vector, DictionaryVector, IntVector } from './vector';
import { Vector, DictionaryVector, IntVector, StructVector } from './vector';
import { ChunkedView } from './vector/chunked';

export type NextFunc = (idx: number, cols: RecordBatch) => void;

Expand Down Expand Up @@ -61,6 +62,13 @@ export class Table implements DataFrame {
}
return Table.empty();
}
static fromStruct(struct: StructVector) {
const schema = new Schema(struct.type.children);
const chunks = struct.view instanceof ChunkedView ?
(struct.view.childVectors as StructVector[]) :
[struct];
return new Table(chunks.map((chunk)=>new RecordBatch(schema, chunk.length, chunk.view.childData)));
}

public readonly schema: Schema;
public readonly length: number;
Expand Down